ppt-visual

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it is designed to ingest and process untrusted data (user-provided slide content) to generate design specifications. This could potentially be exploited if a user provides content containing hidden instructions designed to manipulate the agent's output or the parameters of associated tools.
  • Ingestion points: Untrusted data enters the context through user-provided 'Slide content (text, bullet points)' as described in the 'How to Use Me' section of SKILL.md.
  • Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the user-provided content.
  • Capability inventory: The skill is linked to the 'office-mcp' server, which provides tools with file-writing capabilities such as 'create_pptx' and 'md_to_pptx'.
  • Sanitization: There is no evidence of input validation, escaping, or sanitization of the user-provided content before it is processed.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 05:18 AM